检索结果-内蒙古大学图书馆

33rd International Joint Conference on Artificial Intelligence, IJCAI 2024

作者： Wang, Rui Hu, Chen Chen, Ziheng Wu, Xiao-Jun Song, Xiaoning School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China Department of Information Engineering and Computer Science University of Trento Trento Italy

ISBN: (纸本)9781956792041

In the community of artificial intelligence, significant progress has been made in encoding sequential data using deep learning techniques. Nevertheless, how to effectively mine useful information from channel dimensions remains a major challenge, as these features have a submanifold structure. Linear subspace, the basic element of the Grassmannian manifold, has proven to be an effective manifold-valued feature descriptor in statistical representation. Besides, the Euclidean self-attention mechanism has shown great success in capturing long-range relationships of data. Inspired by these facts, we extend the self-attention mechanism to the Grassmannian manifold. Our framework can effectively characterize the spatiotemporal fluctuations of sequential data encoded in the Grassmannian manifold. Extensive experimental results on three benchmarking datasets (a drone recognition dataset and two EEG signal classification datasets) demonstrate the superiority of our method over the state-of-the-art. The code and supplementary material for this work can be found at https://***/ChenHu-ML/GDLNet. © 2024 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Editorial

引用

International Journal of Bio-Inspired Computation 2020年第2期16卷 67-67页

作者： Fang, Wei Wu, Xiaojun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Department of Computer Science and Technology Jiangnan University 214122 China

来源：评论

学校读者我要写书评

暂无评论

A dual-branch network for infrared and visible image fusion

arXiv

引用

arXiv 2021年

作者： Fu, Yu Wu, Xiao-Jun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China

In recent years, deep learning has been used extensively in the field of image fusion. In this article, we propose a new image fusion method by designing a new structure and a new loss function for a deep learning model. Our backbone network is an autoencoder, in which the encoder has a dual branch structure. We input infrared images and visible light images to the encoder to extract detailed information and semantic information respectively. The fusion layer fuses two sets of features to get fused features. The decoder reconstructs the fusion features to obtain the fused image. We design a new loss function to reconstruct the image effectively. Experiments show that our proposed method achieves state-of-the-art performance. © 2021, CC BY.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Parallel High-Utility Itemset Mining Algorithm Based on Hadoop

引用

Complex System Modeling and Simulation 2023年第1期3卷 47-58页

作者： Zaihe Cheng Wei Shen Wei Fang Jerry Chun-Wei Lin School of Internet of Things Wuxi Institute of TechnologyWuxi 214121China School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan UniversityWuxi 214122China Department of Computer Science Electrical Engineering and Mathematical SciencesWestern Norway University of Applied SciencesBergen 5020Norway

High-utility itemset mining(HUIM)can consider not only the profit factor but also the profitable factor,which is an essential task in data ***,most HUIM algorithms are mainly developed on a single machine,which is inefficient for big data since limited memory and processing capacities are available.A parallel efficient high-utility itemset mining(P-EFIM)algorithm is proposed based on the Hadoop platform to solve this problem in this *** P-EFIM,the transaction-weighted utilization values are calculated and ordered for the itemsets with the MapReduce *** the ordered itemsets are renumbered,and the low-utility itemsets are pruned to improve the dataset *** the Map phase,the P-EFIM algorithm divides the task into multiple independent *** uses the proposed S-style distribution strategy to distribute the subtasks evenly across all nodes to ensure ***,the P-EFIM uses the EFIM algorithm to mine each subtask dataset to enhance the performance in the Reduce *** are performed on eight datasets,and the results show that the runtime performance of P-EFIM is significantly higher than that of the PHUI-Growth,which is also HUIM algorithm based on the Hadoop framework.

关键词： pattern mining data mining Hadoop parallel high-utility itemset mining big data

来源：评论

学校读者我要写书评

暂无评论

Infrared and visible image fusion using Latent Low-Rank Representation

arXiv

引用

arXiv 2018年

作者： Li, Hui Wu, Xiao-Jun Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence School of IoT engineering Jiangnan University Wuxi China

Infrared and visible image fusion is an important problem in the field of image fusion which has been applied widely in many fields. To better preserve the useful information from source images, in this paper, we propose a novel image fusion method based on latent low-rank representation(LatLRR) which is simple and effective. Firstly, the source images are decomposed into low-rank parts(global structure) and salient parts(local structure) by LatLRR. Then, the low-rank parts are fused by weighted-average strategy to preserve more contour information. Then, the salient parts are simply fused by sum strategy which is a efficient operation in this fusion framework. Finally, the fused image is obtained by combining the fused low-rank part and the fused salient part. Compared with other fusion methods experimentally, the proposed method has better fusion performance than state-of-the-art fusion methods in both subjective and objective evaluation. The Code of our fusion method is available at https://***/hli1221/imagefusion_Infrared_visible_latlrr. Copyright © 2018, The Authors. All rights reserved.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Feature Space Renormalization for Semi-supervised Learning

arXiv

引用

arXiv 2023年

作者： Sun, Jun Mao, Zhongjie Li, Chao Zhou, Chao Wu, Xiao-Jun The School of Artificial Intelligence and Computer Science Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University 1800 Lihu Avenue Jiangsu Wuxi214122 China The Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University 1800 Lihu Avenue Jiangsu Wuxi214122 China

Semi-supervised learning (SSL) has been proven to be a powerful method for leveraging unlabelled data to alleviate models' dependence on large labelled datasets. The common framework among recent approaches is to train the model on a large amount of unlabelled data with consistency regularization to constrain the model predictions to be invariant to input perturbation. However, the existing SSL frameworks still have room for improvement in the consistency regularization method. Instead of regularizing category predictions in the label space as in existing frameworks, this paper proposes a feature space renormalization (FSR) mechanism for SSL. First, we propose a feature space renormalization mechanism to substitute for the commonly used consistency regularization mechanism to learn better discriminative features. To apply this mechanism, we start by building a basic model and an empirical model and then introduce our mechanism to renormalize the feature learning of the basic model with the guidance of the empirical model. Second, we combine the proposed mechanism with pseudo-labelling to obtain a novel effective SSL model named FreMatch. The experimental results show that our method can achieve better performance on a variety of standard SSL benchmark datasets, and the proposed feature space renormalization mechanism can also enhance the performance of other SSL approaches. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Low-Complexity Channel Estimation Method Based on ISSOR-PCG for Massive MIMO Systems 8th

Low-Complexity Channel Estimation Method Based on ISSOR-PCG ...

引用

8th International Conference on Communications, Signal Processing, and Systems, CSPS 2019

作者： Zhou, Cheng Li, Zhengquan Wu, Qiong Liu, Yang Li, Baolong Wu, Guilu Zhao, Xiaoqing Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China National Mobile Communication Research Laboratory Southeast University Nanjing210096 China Department of Electronic Engineering Tsinghua University Beijing100084 China The National Key Laboratory of millimeter wave Southeast University Nanjing210096 China

ISBN: (纸本)9789811394089

With the boost of the quantity of antennas at the base station (BS) in massive multiple-input multiple-output (MIMO) systems, the channel capacity and spectral efficiency are also increased. Conventional channel estimation method, such as the classical minimum mean square error (MMSE), which involves the matrix inversion in large size with enormous computational complexity, especially in massive MIMO systems due to large antenna arrays. To degrade the complexity caused by the inversion of the matrix, a low-complexity channel estimation scheme is proposed based on the improved symmetric successive over relaxation preconditioned conjugate gradient (ISSOR-PCG) method to avoid computing the matrix inversion directly. A simple way is also introduced to address the optimal relaxation parameter for the proposed scheme, by utilizing the channel asymptotic orthogonality in massive MIMO systems. Analysis shows that the proposed channel estimator is able to degrade the complexity effectively compared with MMSE channel estimator. Simulation results illustrate that the proposed scheme can obtain near-optimal performance to the classical MMSE estimation method and outperforms other baseline schemes with increased number of iterations. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Mining High Quality patterns Using Multi-Objective Evolutionary Algorithm (Extended Abstract)

Mining High Quality Patterns Using Multi-Objective Evolution...

引用

International Conference on Data engineering

作者： Wei Fang Qiang Zhang Jun Sun Xiaojun Wu International Joint Laboratory on Artificial Intelligence of Jiangsu Province Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

Most studies on pattern mining have considered only one pattern, such as frequent pattern or high-utility pattern, which is difficult to meet the increasingly diverse needs of users. In this paper, a novel multi-objective problem model for high quality pattern mining (HQPM) is proposed, where the objectives are support, occupancy, and utility. In order to solve the proposed three-objective problem efficiently, an improved multi-objective evolutionary algorithm for HQPM (MOEA-PM) is proposed with two kinds of population initialization strategies and an auxiliary tool. Experimental results on real-world datasets show that the proposed three-objective problem model with the MOEA-PM algorithm can discover patterns that are both frequently occurring and has a high utility in the transaction datasets, while at the same time being relatively complete. The proposed algorithm outperforms the state-of-the-art in terms of efficiency, quality, and convergence speed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mutual Information-Guided GA for Bayesian Network Structure Learning (Extended Abstract)

Mutual Information-Guided GA for Bayesian Network Structure ...

引用

International Conference on Data engineering

作者： Kefei Yan Wei Fang Hengyang Lu Xin Zhang Jun Sun Xiaojun Wu Department of Computer Science and Technology Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Bayesian network structure learning (BNSL) from data is an NP-hard problem. Genetic algorithms are powerful for solving combinatorial optimization problems, but the lack of effective guidance results in slow convergence and low accuracy regarding BNSL. To address this problem, we propose a mutual information (MI) guided genetic algorithm (MIGA) for BNSL in this paper, which uses MI to effectively search BN structures. In the initialization phase of MIGA, the population is generated by adding additional constraints based on MI to reach a higher score without losing diversity. By employing normalized MI and defining the population support, the potential dominance in the population can be identified and then used to design a novel crossover operator in order to preserve the dominant genes with a higher probability. Moreover, with the guidance of MI for removing loops from the structures, infeasible solutions can be handled in a straightforward and practical way. The proposed MIGA is evaluated on eleven well-known benchmark datasets and compared with four GA-based methods and four other state-of-the-art BNSL algorithms. Experimental results show that MIGA outperforms the compared algorithms in convergence and learning accuracy.

关键词： Accuracy NP-hard problem Sociology Search problems Bayes methods Statistics Optimization

来源：评论

学校读者我要写书评

暂无评论

DreamNet: A Deep Riemannian Manifold Network for SPD Matrix Learning 16th

DreamNet: A Deep Riemannian Manifold Network for SPD Matrix...

引用

16th Asian Conference on Computer Vision, ACCV 2022

作者： Wang, Rui Wu, Xiao-Jun Chen, Ziheng Xu, Tianyang Kittler, Josef School of Artificial Intelligence and Computer Science Jiangnan University Wuxi214122 China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Jiangnan University Wuxi214122 China University of Surrey GuildfordGU2 7XH United Kingdom

ISBN: (纸本)9783031263507

The methods of symmetric positive definite (SPD) matrix learning have attracted considerable attention in many pattern recognition tasks, as they are eligible to capture and learn appropriate statistical features while respecting the Riemannian geometry of SPD manifold where the data reside on. Accompanied with the advanced deep learning techniques, several Riemannian networks (RiemNets) for SPD matrix nonlinear processing have recently been studied. However, it is pertinent to ask, whether greater accuracy gains can be realized by simply increasing the depth of RiemNets. The answer appears to be negative, as deeper RiemNets may be difficult to train. To explore a possible solution to this issue, we propose a new architecture for SPD matrix learning. Specifically, to enrich the deep representations, we build a stacked Riemannian autoencoder (SRAE) on the tail of the backbone network, i.e., SPDNet [23]. With this design, the associated reconstruction error term can prompt the embedding functions of both SRAE and of each RAE to approach an identity mapping, which helps to prevent the degradation of statistical information. Then, we implant several residual-like blocks using shortcut connections to augment the representational capacity of SRAE, and to simplify the training of a deeper network. The experimental evidence demonstrates that our DreamNet can achieve improved accuracy with increased depth. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：